Paper Citation Record · LEDGER

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures

As of 22 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2607.17138.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.17138 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T18:58:31.144233Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

14 of 14 outbound references displayed

verified exact1
verified fuzzy0
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 52b9ef24-329d-47a4-a245-860b88dd4593 · outbound

This paper cites Predictive coding feedback results in perceived illusory contours in a recurrent neural network.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Predictive coding feedback results in perceived illusory contours in a recurrent neural network

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:29.447714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef0712bc-fec3-4fb7-9e92-4f647abaf914 · outbound

This paper cites This preserves the local target-object appearance while disrupting the far surround context.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures This preserves the local target-object appearance while disrupting the far surround context

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.825423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c98f3d6-81c2-4bf0-afbe-7da1f0621950 · outbound

This paper cites URL https://www.nature.com/articles/s41598-024-52423-7.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures URL https://www.nature.com/articles/s41598-024-52423-7

Reference 5

Resolution: verified exact; doi, observed 2026-08-01T19:03:29.563572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 57b245f9-95fb-4e7f-bca4-e43fd872690b · outbound

This paper cites Designing and interpreting probes with control tasks.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Designing and interpreting probes with control tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.097957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0591156f-052a-4ef8-ba15-9b74ec50aef1 · outbound

This paper cites Intriguing properties of generative classifiers.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Intriguing properties of generative classifiers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.406039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca08711-823a-426c-9765-ad28cd86c543 · outbound

This paper cites All analyses use only the 35 base images (filter: ’flip’ not in name and not name.endswith(’_r’) ).

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures All analyses use only the 35 base images (filter: ’flip’ not in name and not name.endswith(’_r’) )

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.684662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9bbd22-871e-4dbd-8d0e-0cb968f04f8e · outbound

This paper cites [2023], vl-illusion/GVIL Pyllusion (parametric stimuli li- brary) MITRealityBending/Pyllusion Makowski et al.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures [2023], vl-illusion/GVIL Pyllusion (parametric stimuli li- brary) MITRealityBending/Pyllusion Makowski et al

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.982624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d77d9ed-ba34-4ddb-be03-ac76c5dd8330 · outbound

This paper cites The CreativeML OpenRAIL-M license on Stable Diffusion 1.5 includes use-based behavioral restrictions (no harmful or deceptive use), which our diagnostic probing does not violate.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures The CreativeML OpenRAIL-M license on Stable Diffusion 1.5 includes use-based behavioral restrictions (no harmful or deceptive use), which our diagnostic probing does not violate

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:31.144233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4486ff1d-8abe-4b85-8c23-4aaee075e924 · outbound

This paper cites doi: 10.18653/v1/D19-1275.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures doi: 10.18653/v1/D19-1275

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.231493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8253b53e-4a83-4b73-b93b-373706cc16a3 · outbound

This paper cites URL https://aclanthology.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures URL https://aclanthology

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:29.786717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b1a52d-b6b6-41ff-9fe7-6ecf96f5cd9a · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.566297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bfc993f-2e67-4949-8221-d77f98e3a6f7 · outbound

This paper cites Towards Automated Circuit Discovery for Mechanistic Interpretability.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:29.659933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0adb8689-5625-45a9-ab61-40f7745fb47a · outbound

This paper cites Measuring the reliability of causal probing methods: Tradeoffs, limitations, and the plight of nullifying interventions.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures Measuring the reliability of causal probing methods: Tradeoffs, limitations, and the plight of nullifying interventions

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:29.575395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b820aea0-75d9-4a26-823e-a72699e6834e · outbound

This paper cites The Art of Deception: Color Visual Illusions and Diffusion Models.

Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures The Art of Deception: Color Visual Illusions and Diffusion Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T18:58:30.012275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.